IEEE

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection

Abstract: Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time series ...
GitHub

This the open-source code for KDD' 24 IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks.

The folder IDEA includes implementations of IDEA (folder src) and scripts supporting the reported experiments. Run the following command to reproduce the reported experiments. ./1_bounds.sh # ...
Ulster University

Accelerating your Research using the Northern Ireland HPC cluster: Hands-on guide with GPU and CPU-based applications - Part 2

This workshop will consider several applications based on machine learning classification and the training of artificial neural networks and deep learning.